whatmodel.sh · find the best AI models you can run

AI models in the GPQA Diamond model set

A leaderboard of the best AI models. Models are ranked by one score that combines 575 published benchmarks. Filter by your computer or budget to find the best one you can use.

Filter by your hardware and budget

ram[2][4][8][16][24][32][48][64][96][128][192][256]GB

gpu[apple silicon][graphics card][unified memory][none]

price[local][$0.02][$0.1][$0.5][$2][$10][$50][any]max per M

Filter by task

task[all tasks][agent tasks][coding][chat & writing][math][vision & documents][web search]

New #1s:

orRSS

detecting your OS…

$ terminal

#	model	score↓	where↓	RAM↓	speed↓	context↓	get it	sources

#	model	score↓	where↓	RAM↓	speed↓	context↓	get it	sources
—	LFM2.5 24B-A2B Liquid AI	not yet calibrated	local	~17GB		131k	llama.cpp ›
—	LFM3 1.7B Liquid AI	not yet calibrated	local	~2.6GB		262k	llama.cpp ›

2 of 1227 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory